Unlocking the Language of Cells

CellWhisperer bridges the gap between transcriptomics data and natural language, enabling intuitive interaction with scRNA-seq datasets.

Decipher single cells from the
Tabula Sapiens dataset
Explore
human transcriptomes in GEO
Chat with the
colonic epithelium
Analyze
embryonic development
Spotlight paper @ ICLR 2024 MLGenX BioRxiv Code Datasets & Models Analyze your own data

Tutorial

(Click the annotated screenshot for a 2-minute video-tutorial)

Annotated screenshot of CellWhisperer application

CellWhisperer constitutes a proof-of-concept for interactive exploration of scRNA-seq data. Like other AI models, CellWhisperer does not understand user questions in a human sense, and it can make mistakes. Key results should thus be reconfirmed with conventional bioinformatics approaches.

Analyze your own data

The CellWhisperer server linked above provides example datasets but does not allow for upload of user-provided datasets. To analyze your own data with CellWhisperer, you need to run CellWhisperer on your computer or on a local server. This is relatively straightforward to set up in three steps:

  1. Prepare your scRNA-seq data as an h5ad file
  2. Run the CellWhisperer data processing script
  3. Launch CellWhisperer on your computer and add the dataset

A step-by-step description is provided in the CellWhisperer GitHub repository.

News

Citation

If you use CellWhisperer in your research, please cite us:

Moritz Schaefer*, Peter Peneder*, Daniel Malzl, Salvo Danilo Lombardo, Mihaela Peycheva, Jake Burton, Anna Hakobyan, Varun Sharma, Thomas Krausgruber, Celine Sin, Jörg Menche, Eleni M. Tomazou, Christoph Bock (2025) Multimodal learning enables chat-based exploration of single-cell data. Nature Biotechnology (in press). DOI: 10.1038/s41587-025-02857-9

* equal contribution

Preprint: bioRxiv

Feedback

Got feedback? Drop us an email at cellwhisperer@bocklab.org or open an issue on GitHub.